当我们在暗网中实现 YOLOv2 时，每 10 个 epoch 之后，图像大小就会发生变化。这是怎么回事？
When we implement YOLOv2 in darknet, after every 10 epochs, the image size is changed. How is this happening?
在 YOLO v2 中，每 10 个 epoch 之后，网络会随机选择一个大小，这在暗网中是如何发生的？我正在使用 ubuntu 18.04
我认为网络大小每 10 次迭代（而不是 epochs）改变一次。
在您的 cfg 文件中，检查 random 标志。
random = 1 表示 Yolo 每 10 次迭代更改网络大小，通过在不同分辨率下训练网络来提高精度很有用。
根据 Yolo 论文：
However, since our model only uses convolutional and pooling layers it
can be resized on the fly. We want YOLOv2 to be robust to running on
images of different sizes so we train this into the model. Instead of
fixing the input image size we change the network every few
iterations. Every 10 batches our network randomly chooses a new image
dimension size. Since our model downsamples by a factor of 32, we pull
from the following multiples of 32: {320, 352, ..., 608}. Thus the
smallest option is 320 × 320 and the largest is 608 × 608. We resize
the network to that dimension and continue training.
在 YOLO v2 中，每 10 个 epoch 之后，网络会随机选择一个大小，这在暗网中是如何发生的？我正在使用 ubuntu 18.04
我认为网络大小每 10 次迭代（而不是 epochs）改变一次。
在您的 cfg 文件中，检查 random 标志。
random = 1 表示 Yolo 每 10 次迭代更改网络大小，通过在不同分辨率下训练网络来提高精度很有用。
根据 Yolo 论文：
However, since our model only uses convolutional and pooling layers it can be resized on the fly. We want YOLOv2 to be robust to running on images of different sizes so we train this into the model. Instead of fixing the input image size we change the network every few iterations. Every 10 batches our network randomly chooses a new image dimension size. Since our model downsamples by a factor of 32, we pull from the following multiples of 32: {320, 352, ..., 608}. Thus the smallest option is 320 × 320 and the largest is 608 × 608. We resize the network to that dimension and continue training.